Capacity Analysis of MIMO-STBC System in the Presence of Nonlinear Distortion and Neural Network Compensator

Abstract:
Multiple Input Multiple Output (MIMO) is a promising candidate for the future generation communication networks. It has been proposed to develop wireless systems that offer both high capacity and good performance. To achieve high date rate and fulfill the power, MIMO systems are equipped with High Power Amplifiers (HPA). Unfortunately, the nonlinearity of HPA has a crucial impact and affects the receiver’s performance. Since a few decades, Neural Networks (NN) have shown excellent performance in solving various of complex problems (such as classification, recognition, approximation, etc.). In this paper, we focus on HPA nonlinearity in MIMO Space Time Block Coding (STBC) systems. Then, we propose a receiver scheme based on NN technique in conjunction with Maximal Ratio Combining (MRC) to compensate HPA nonlinearity. The performance of the proposed scheme are evaluated in a MIMO-STBC system, running under uncorrelated Rayleigh fading channels, in term of system capacity.Water-filling (WF) and lower bound (LB) solutions are considered. Simulation results show the accuracy of the proposed receiver in improvement of system capacity and confirm our analytic approach.